Squidpy preprocessing analysis - run5

Zhiyuan Hu
15 jul 2024
Refer to https://squidpy.readthedocs.io/en/stable/notebooks/tutorials/tutorial_vizgen.html

import datetime
## last modified
current_date = datetime.datetime.now().strftime("%B %d, %Y")
current_time = datetime.datetime.now().strftime("%I:%M %p")
current_date + ", "+current_time

'July 15, 2024, 09:03 AM'

from pathlib import Path

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns
import anndata

import scanpy as sc
import squidpy as sq

sc.logging.print_header()

/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

scanpy==1.9.5 anndata==0.10.1 umap==0.5.4 numpy==1.26.4 scipy==1.11.3 pandas==2.2.1 scikit-learn==1.3.2 statsmodels==0.14.0 igraph==0.9.11 pynndescent==0.5.10

To merge multiple regions in the same run, refer to: https://discourse.scverse.org/t/how-to-concatenate-spatial-anndata-objects/1638

vizgen_dir = "/home/huzhiy/projects_ox/merscope/merscope_run5/data/raw_data/"

adatas_vis = {
  "region_0": sq.read.vizgen(vizgen_dir+"region_0"+"/analysis_output_cp2",counts_file="cell_by_gene.csv",meta_file="cell_metadata.csv", transformation_file="micron_to_mosaic_pixel_transform.csv"),
  "region_1": sq.read.vizgen(vizgen_dir+"region_1"+"/analysis_output_cp2",counts_file="cell_by_gene.csv",meta_file="cell_metadata.csv", transformation_file="micron_to_mosaic_pixel_transform.csv"),
  "region_2": sq.read.vizgen(vizgen_dir+"region_2"+"/analysis_output_cp2",counts_file="cell_by_gene.csv",meta_file="cell_metadata.csv", transformation_file="micron_to_mosaic_pixel_transform.csv"),
  "region_3": sq.read.vizgen(vizgen_dir+"region_3"+"/analysis_output_cp2",counts_file="cell_by_gene.csv",meta_file="cell_metadata.csv", transformation_file="micron_to_mosaic_pixel_transform.csv"),
  "region_4": sq.read.vizgen(vizgen_dir+"region_4"+"/analysis_output_cp2",counts_file="cell_by_gene.csv",meta_file="cell_metadata.csv", transformation_file="micron_to_mosaic_pixel_transform.csv"),
  "region_5": sq.read.vizgen(vizgen_dir+"region_5"+"/analysis_output_cp2",counts_file="cell_by_gene.csv",meta_file="cell_metadata.csv", transformation_file="micron_to_mosaic_pixel_transform.csv")}

adata = anndata.concat(adatas_vis, index_unique="_", merge="same", uns_merge="unique")

/home/huzhiy/.local/lib/python3.10/site-packages/anndata/_core/merge.py:1242: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  concat_indices = concat_indices.str.cat(label_col.map(str), sep=index_unique)

adata

AnnData object with n_obs × n_vars = 134789 × 300
    obs: 'fov', 'volume', 'min_x', 'min_y', 'max_x', 'max_y', 'anisotropy', 'transcript_count', 'perimeter_area_ratio', 'solidity'
    obsm: 'blank_genes', 'spatial'

# read MERSCOPE visualizer-exported data
anndata_filename = "/home/huzhiy/projects_ox/merscope/merscope_run5/data/raw_data/15-07-24_09-00_run5_reseg_cell.hdf5"
adata2 = sc.read_h5ad(anndata_filename)

adata2

AnnData object with n_obs × n_vars = 134789 × 315
    obs: 'Custom cell groups', 'Datasets', 'volume', 'center_x', 'center_y'
    uns: 'Custom cell groups_colors', 'Datasets_colors'

calculate QC metrics

sc.pp.calculate_qc_metrics(adata, percent_top=(50, 100, 200, 280), inplace=True)

adata.obsm["blank_genes"].to_numpy().sum() / adata.var["total_counts"].sum() * 100

0.23369169794023037

# Next we plot the distribution of total transcripts per cell, unique transcripts per cell, transcripts per FOV and the volume of the segmented cells
fig, axs = plt.subplots(1, 4, figsize=(15, 4))

axs[0].set_title("Total transcripts per cell")
sns.histplot(
    adata.obs["total_counts"],
    kde=False,
    ax=axs[0],
)

axs[1].set_title("Unique transcripts per cell")
sns.histplot(
    adata.obs["n_genes_by_counts"],
    kde=False,
    ax=axs[1],
)

axs[2].set_title("Transcripts per FOV")
sns.histplot(
    adata.obs.groupby("fov").sum()["total_counts"],
    kde=False,
    ax=axs[2],
)

axs[3].set_title("Volume of segmented cells")
sns.histplot(
    adata.obs["volume"],
    kde=False,
    ax=axs[3],
)

<Axes: title={'center': 'Volume of segmented cells'}, xlabel='volume', ylabel='Count'>

sc.pp.filter_cells(adata, min_counts=10)

ser_volume = adata.obs['volume']
# filter cells based on volume
min_volume = 50
keep_cells = ser_volume[ser_volume > min_volume].index.tolist()
adata = adata[keep_cells]

ser_volume = adata.obs['volume']
ser_volume.hist(bins=100)

<Axes: >

adata

View of AnnData object with n_obs × n_vars = 106333 × 300
    obs: 'fov', 'volume', 'min_x', 'min_y', 'max_x', 'max_y', 'anisotropy', 'transcript_count', 'perimeter_area_ratio', 'solidity', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'pct_counts_in_top_50_genes', 'pct_counts_in_top_100_genes', 'pct_counts_in_top_200_genes', 'pct_counts_in_top_280_genes', 'n_counts'
    var: 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts'
    obsm: 'blank_genes', 'spatial'

adata.layers["counts"] = adata.X.copy()
# sc.pp.highly_variable_genes(adata, flavor="seurat_v3", n_top_genes=4000)
# sc.pp.normalize_total(adata, inplace=True)
# sc.pp.log1p(adata)
# sc.pp.pca(adata)
# sc.pp.neighbors(adata)
# sc.tl.umap(adata)
# sc.tl.leiden(adata)

resolution = 1.5

# Leiden Clustering
######################

# dividing by volume instead
sc.pp.normalize_total(adata)
sc.pp.log1p(adata)
sc.pp.scale(adata, max_value=10)
sc.tl.pca(adata, svd_solver='arpack')
sc.pp.neighbors(adata, n_neighbors=10, n_pcs=20)
sc.tl.umap(adata)
sc.tl.leiden(adata, resolution=resolution)

# Calculate Leiden Signatures
#########################################df_pos.index = [str(x) for x in list(range(df_pos.shape[0]))]
ser_counts = adata.obs['leiden'].value_counts()
ser_counts.name = 'cell counts'
meta_leiden = pd.DataFrame(ser_counts)

cat_name = 'leiden'
sig_leiden = pd.DataFrame(columns=adata.var_names, index=adata.obs[cat_name].cat.categories)
for clust in adata.obs[cat_name].cat.categories:
    sig_leiden.loc[clust] = adata[adata.obs[cat_name].isin([clust]),:].X.mean(0)
sig_leiden = sig_leiden.transpose()
leiden_clusters = ['Leiden-' + str(x) for x in sig_leiden.columns.tolist()]
sig_leiden.columns = leiden_clusters
meta_leiden.index = sig_leiden.columns.tolist()
meta_leiden['leiden'] = pd.Series(meta_leiden.index.tolist(), index=meta_leiden.index.tolist())

# generate colors for categories by plotting
sc.pl.umap(adata, color="leiden", legend_loc='on data')
cats = adata.obs['leiden'].cat.categories.tolist()
colors = list(adata.uns['leiden_colors'])
cat_colors = dict(zip(cats, colors))

# colors for clustergrammer2
ser_color = pd.Series(cat_colors)
ser_color.name = 'color'
df_colors = pd.DataFrame(ser_color)
df_colors.index = ['Leiden-' + str(x) for x in df_colors.index.tolist()]

df_colors.loc[''] = 'white'

/tmp/ipykernel_20744/88863033.py:1: ImplicitModificationWarning: Setting element `.layers['counts']` of view, initializing view as actual.
  adata.layers["counts"] = adata.X.copy()
/home/huzhiy/.local/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/home/huzhiy/.local/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

Visualize annotation on UMAP and spatial coordinates

sc.pl.umap(
    adata,
    color=[
        "total_counts",
        "n_genes_by_counts",
        "leiden",
    ],
    wspace=0.4,
)

/home/huzhiy/.local/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/home/huzhiy/.local/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

sq.pl.spatial_scatter(
    adata,
    shape=None,
    color=[
        "leiden",
    ],
    wspace=0.4,size = 0.3, figsize=[16,20]
)

WARNING: Please specify a valid `library_id` or set it permanently in `adata.uns['spatial']`

/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:483: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = color_source_vector.map(color_map)
/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:956: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap', 'norm' will be ignored
  _cax = scatter(

adata

AnnData object with n_obs × n_vars = 106333 × 300
    obs: 'fov', 'volume', 'min_x', 'min_y', 'max_x', 'max_y', 'anisotropy', 'transcript_count', 'perimeter_area_ratio', 'solidity', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'pct_counts_in_top_50_genes', 'pct_counts_in_top_100_genes', 'pct_counts_in_top_200_genes', 'pct_counts_in_top_280_genes', 'n_counts', 'leiden'
    var: 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts', 'mean', 'std'
    uns: 'log1p', 'pca', 'neighbors', 'umap', 'leiden', 'leiden_colors'
    obsm: 'blank_genes', 'spatial', 'X_pca', 'X_umap'
    varm: 'PCs'
    layers: 'counts'
    obsp: 'distances', 'connectivities'

adata.obs

	fov	volume	min_x	min_y	max_x	max_y	anisotropy	transcript_count	perimeter_area_ratio	solidity	n_genes_by_counts	log1p_n_genes_by_counts	total_counts	log1p_total_counts	pct_counts_in_top_50_genes	pct_counts_in_top_100_genes	pct_counts_in_top_200_genes	pct_counts_in_top_280_genes	n_counts	leiden
2966051100000200090_region_0	NaN	441.034902	11540.829358	7438.750940	11547.937591	7446.439018	1.017014	NaN	0.555498	1.000000	8	2.197225	12.0	2.564949	100.000000	100.0	100.0	100.0	12.0	2
2966051100000200106_region_0	NaN	609.664956	11624.564163	7470.680053	11632.931726	7479.615065	1.094903	NaN	0.471427	1.000000	24	3.218876	33.0	3.526361	100.000000	100.0	100.0	100.0	33.0	28
2966051100000200108_region_0	NaN	592.042394	11618.702198	7481.613759	11626.991857	7490.507182	1.017678	NaN	0.478782	1.000000	8	2.197225	11.0	2.484907	100.000000	100.0	100.0	100.0	11.0	19
2966051100003200032_region_0	NaN	296.786645	12989.833574	7400.539093	12996.010412	7406.590181	1.238560	NaN	0.707109	1.000000	58	4.077537	90.0	4.510859	91.111111	100.0	100.0	100.0	90.0	5
2966051100003200033_region_0	NaN	310.239655	12974.849513	7400.932285	12981.122590	7407.241858	1.084988	NaN	0.681291	1.000000	77	4.356709	160.0	5.081404	83.125000	100.0	100.0	100.0	160.0	5
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2967874700065200174_region_5	NaN	1450.861926	3153.838448	4822.005816	3167.979714	4835.923483	1.081753	NaN	0.316526	0.991420	37	3.637586	54.0	4.007333	100.000000	100.0	100.0	100.0	54.0	6
2967874700065200191_region_5	NaN	2323.318400	2963.153843	4939.870350	2979.615168	4958.585936	1.325447	NaN	0.246470	0.996045	64	4.174387	208.0	5.342334	93.269231	100.0	100.0	100.0	208.0	16
2967874700065200198_region_5	NaN	1867.564157	2895.398785	4975.914949	2911.030914	4990.450365	1.114777	NaN	0.273560	0.995428	47	3.871201	106.0	4.672829	100.000000	100.0	100.0	100.0	106.0	2
2967874700066200050_region_5	NaN	664.776531	3402.564821	4744.479315	3412.345087	4752.659208	1.195099	NaN	0.453776	0.999481	17	2.890372	23.0	3.178054	100.000000	100.0	100.0	100.0	23.0	2
2967874700066200074_region_5	NaN	1198.814193	3385.825051	4769.637610	3400.217751	4783.424266	2.063652	NaN	0.388846	0.941395	19	2.995732	23.0	3.178054	100.000000	100.0	100.0	100.0	23.0	9

106333 rows × 20 columns

Assign sections

Because there is a huge difference in the stage and genotype; making it difficult to precise map between scRNA-seq/snRNA-seq

Thus we need to annoate cells by their locations

import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import SpectralClustering
from matplotlib.ticker import FuncFormatter

# Set the size of the dots and the figure size
dot_size = 10
fig_size = (10, 6)

# Create a larger figure
plt.figure(figsize=fig_size)

# Plot the points
coordinates=adata.obsm['spatial']
plt.scatter(coordinates[:, 0], coordinates[:, 1], s=dot_size)
# Adjust the grid spacing
plt.xticks(np.arange(300, 15000, 200), rotation=90)  # Adjust the range and spacing as needed
#plt.gca().xaxis.set_major_formatter(FuncFormatter(lambda x, _: f'{x/1000:.0f}k'))

plt.yticks(np.arange(500, 10000, 200))  # Adjust the range and spacing as needed

# Draw your lines manually by specifying the coordinates
# For example, a line from (x1, y1) to (x2, y2) would be:
# plt.plot([x1, x2], [y1, y2], color='red')

# Add more lines as needed

plt.grid(True)

plt.show()

By comparing against the annotation, the left - fli1a/elk3 KO and the right - erf/erfl3

import numpy as np
import matplotlib.pyplot as plt

# Function to assign labels based on x and y values
def label_point(x, y):
    if x < 5500 and y < 6100:
        return 'Region0'
    elif x < 5500 and y >= 6100:
        return 'Region1'
    elif 5500 <= x < 10900 and y < 6100:
        return 'Region2'
    elif 5500 <= x < 10900 and y >= 6100:
        return 'Region3'
    elif x >= 10900 and y < 6100:
        return 'Region4'
    elif x >= 10900 and y >= 6100:
        return 'Region5'
    else:
        return ''

# Assign labels to each point based on the x and y values
labels = np.array([label_point(x, y) for x, y in coordinates])

# Plot the points with colors based on labels
plt.figure(figsize=(12, 10))
unique_labels = np.unique(labels)
colors = plt.cm.viridis(np.linspace(0, 1, len(unique_labels)))
label_to_color = dict(zip(unique_labels, colors))
colored_labels = np.array([label_to_color[label] for label in labels])
scatter = plt.scatter(coordinates[:, 0], coordinates[:, 1], c=colored_labels, s=10)

# Add the partition lines
plt.axvline(x=5500, linestyle='--', color='red')
plt.axvline(x=10900, linestyle='--', color='red')
plt.axhline(y=6100, linestyle='--', color='red')

# Adjust the grid spacing and format y-axis ticks
plt.xticks(np.arange(100, 17000, 200), rotation=90)  # Adjust the range and spacing as needed
#plt.gca().xaxis.set_major_formatter(FuncFormatter(lambda x, _: f'{x/1000:.0f}k'))
plt.yticks(np.arange(100, 12000, 200))  # Adjust the range and spacing as needed

# Set the axis limits
plt.xlim(0, 17000)
plt.ylim(0, 12000)
plt.grid(True)

# Create a legend
handles = [plt.Line2D([0], [0], marker='o', color='w', markerfacecolor=color, markersize=10, label=label)
           for label, color in label_to_color.items()]
plt.legend(handles=handles, title='Regions')

plt.show()

labels

array(['Region5', 'Region5', 'Region5', ..., 'Region0', 'Region0',
       'Region0'], dtype='<U7')

# assign the groups to anndata
adata.obs["regions"] = labels

sq.pl.spatial_scatter(
    adata,
    shape=None,
    color=[
        "regions",
    ],
    wspace=0.4,size = 0.3, figsize=[8,10]
)

WARNING: Please specify a valid `library_id` or set it permanently in `adata.uns['spatial']`

/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:483: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = color_source_vector.map(color_map)
/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:956: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap', 'norm' will be ignored
  _cax = scatter(

sc.pl.umap(
    adata,
    color=[
        "regions",
    ],
    wspace=0.8,
)

/home/huzhiy/.local/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/home/huzhiy/.local/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

Computation of spatial statistics

Building the spatial neighbors graphs

#compute a connectivity matrix from spatial coordinates to calculate the centrality scores
sq.gr.spatial_neighbors(adata, coord_type="generic", delaunay=True)

Compute centrality scores

sq.gr.centrality_scores(adata, cluster_key="leiden")

sq.pl.centrality_scores(adata, cluster_key="leiden", figsize=(16, 5))

/home/huzhiy/.local/lib/python3.10/site-packages/IPython/core/events.py:93: UserWarning: constrained_layout not applied because axes sizes collapsed to zero.  Try making figure larger or axes decorations smaller.
  func(*args, **kwargs)
/home/huzhiy/.local/lib/python3.10/site-packages/IPython/core/pylabtools.py:152: UserWarning: constrained_layout not applied because axes sizes collapsed to zero.  Try making figure larger or axes decorations smaller.
  fig.canvas.print_figure(bytes_io, **kw)

Compute co-occurrence probability

adata_subsample = sc.pp.subsample(adata, fraction=0.5, copy=True)

sq.gr.co_occurrence(
    adata_subsample,
    cluster_key="leiden",
)
sq.pl.co_occurrence(
    adata_subsample,
    cluster_key="leiden",
    clusters="12",
    figsize=(10, 10),
)

WARNING: `n_splits` was automatically set to `26` to prevent `53166x53166` distance matrix from being created

100%|██████████| 351/351 [01:58<00:00,  2.97/s]
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)

sq.pl.spatial_scatter(
    adata_subsample,
    color="leiden",
    shape=None,figsize=(12,12),
    size=1,
)

WARNING: Please specify a valid `library_id` or set it permanently in `adata.uns['spatial']`

/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:483: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = color_source_vector.map(color_map)
/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:956: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap', 'norm' will be ignored
  _cax = scatter(

Neighbors enrichment analysis

sq.gr.nhood_enrichment(adata, cluster_key="leiden")

100%|██████████| 1000/1000 [00:08<00:00, 115.19/s]

fig, ax = plt.subplots(1, 2, figsize=(13, 7))
sq.pl.nhood_enrichment(
    adata,
    cluster_key="leiden",
    figsize=(8, 8),
    title="Neighborhood enrichment adata",
    ax=ax[0],
)
sq.pl.spatial_scatter(adata_subsample, color="leiden", shape=None, size=2, ax=ax[1])

/home/huzhiy/.local/lib/python3.10/site-packages/anndata/_core/anndata.py:522: FutureWarning: The dtype argument is deprecated and will be removed in late 2024.
  warnings.warn(
/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_utils.py:557: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`
  row_labels = adata.obs[key][row_order]

WARNING: Please specify a valid `library_id` or set it permanently in `adata.uns['spatial']`

/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:483: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = color_source_vector.map(color_map)
/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:956: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap', 'norm' will be ignored
  _cax = scatter(

Compute Ripley’s statistics

## determine whether points have a random, dispersed or clustered distribution pattern at certain scale
fig, ax = plt.subplots(1, 2, figsize=(15, 7))
mode = "L"

sq.gr.ripley(adata, cluster_key="leiden", mode=mode)
sq.pl.ripley(adata, cluster_key="leiden", mode=mode, ax=ax[0])

sq.pl.spatial_scatter(
    adata_subsample,
    color="leiden",
    groups=["11", "22", "10"],
    shape=None,
    size=2,
    ax=ax[1],
)

/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)
/home/huzhiy/.local/lib/python3.10/site-packages/seaborn/_base.py:948: FutureWarning: When grouping with a length-1 list-like, you will need to pass a length-1 tuple to get_group in a future version of pandas. Pass `(name,)` instead of `name` to silence this warning.
  data_subset = grouped_data.get_group(pd_key)

WARNING: Please specify a valid `library_id` or set it permanently in `adata.uns['spatial']`

/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_graph.py:318: FutureWarning: 

The `ci` parameter is deprecated. Use `errorbar='sd'` for the same effect.

  sns.lineplot(y="stats", x="bins", ci="sd", alpha=0.01, color="gray", data=res["sims_stat"], ax=ax)
/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:483: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = color_source_vector.map(color_map)
/home/huzhiy/miniforge3/envs/squidpy/lib/python3.10/site-packages/squidpy/pl/_spatial_utils.py:956: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap', 'norm' will be ignored
  _cax = scatter(

Compute Moran’s I score

sq.gr.spatial_neighbors(adata_subsample, coord_type="generic", delaunay=True)
sq.gr.spatial_autocorr(
    adata_subsample,
    mode="moran",
    n_perms=100,
    n_jobs=1,
)
adata_subsample.uns["moranI"].head(10)

100%|██████████| 100/100 [01:31<00:00,  1.10/s]

	I	pval_norm	var_norm	pval_z_sim	pval_sim	var_sim	pval_norm_fdr_bh	pval_z_sim_fdr_bh	pval_sim_fdr_bh
fn1b	0.756368	0.0	0.000006	0.0	0.009901	0.000015	0.0	0.0	0.009901
rx1	0.723111	0.0	0.000006	0.0	0.009901	0.000010	0.0	0.0	0.009901
tbx6	0.703416	0.0	0.000006	0.0	0.009901	0.000014	0.0	0.0	0.009901
ntd5	0.637255	0.0	0.000006	0.0	0.009901	0.000013	0.0	0.0	0.009901
zic2a	0.630203	0.0	0.000006	0.0	0.009901	0.000011	0.0	0.0	0.009901
fezf2	0.612009	0.0	0.000006	0.0	0.009901	0.000010	0.0	0.0	0.009901
klhl41b	0.601708	0.0	0.000006	0.0	0.009901	0.000010	0.0	0.0	0.009901
unc45b	0.601579	0.0	0.000006	0.0	0.009901	0.000015	0.0	0.0	0.009901
wnt5b	0.591393	0.0	0.000006	0.0	0.009901	0.000013	0.0	0.0	0.009901
ncam1a	0.584292	0.0	0.000006	0.0	0.009901	0.000011	0.0	0.0	0.009901

sq.pl.spatial_scatter(
    adata_subsample,
    color=[
        "tbx6",
        "fn1b",
        "klhl41b",
        "unc45b",
        "ncam1b",
        "nkx2.4a"
    ],
    shape=None,
    size=2,
    img=False,
)

WARNING: Please specify a valid `library_id` or set it permanently in `adata.uns['spatial']`

sq.pl.spatial_scatter(
    adata_subsample,
    color=[
        "foxd3","tfap2a","sox10"
    ],
    shape=None,
    size=2,
    img=False,
)

WARNING: Please specify a valid `library_id` or set it permanently in `adata.uns['spatial']`

Assign rough Cell Types (less accurate)

Reference Cell Type Marker Gene Sets

gene_panel = "/home/huzhiy/projects_ox/merscope/analysis/clustering_mapping/data/gene_metadata_manual.csv"
df_ref_panel_ini = pd.read_csv(gene_panel, index_col=0)
df_ref_panel = df_ref_panel_ini.iloc[0:, :1]
df_ref_panel.index.name = None
df_ref_panel.columns = ["Function"]

df_ref_panel

	Function
dlx2a	mNC_arch2,mNC_arch1,differentiating neurons - ...
foxc1a	mNC_head_mesenchymal,mesoderm lateral plate - ...
postnb	mNC_head_mesenchymal marker
grem2b	mNC_arch1 marker
bhlhe40	retina pigmented epithelium marker
...	...
itm2cb	tailbud - PSM marker
pax6b	tailbud - spinal cord marker
fhl2a	heart mature marker
gata5	mesoderm - lateral plate - cxcl12a,mesoderm - ...
gata1a	mesoderm - blood island marker

174 rows × 1 columns

from copy import deepcopy


# Assign marker gene metadata using reference dataset
marker_genes = df_ref_panel[
    df_ref_panel["Function"].str.contains("marker")
].index.tolist()
# marker_genes = df_ref_panel.index.tolist()

meta_gene = deepcopy(adata.var)
common_marker_genes = list(set(meta_gene.index.tolist()).intersection(marker_genes))
meta_gene.loc[common_marker_genes, "Markers"] = df_ref_panel.loc[
    common_marker_genes, "Function"
]

meta_gene["Markers"] = meta_gene["Markers"].apply(
    lambda x: "N.A." if "marker" not in str(x) else x
)
meta_gene["Markers"].value_counts()

Markers
N.A.                                                     126
NPB_hox3 marker                                            6
mNC_nohox marker                                           5
mNC_head_mesenchymal marker                                5
dNC_hox34 marker                                           5
                                                        ... 
mNC_vagal,Mutant_nohox_early marker                        1
mNC_vagal,Mutant_hox3 marker                               1
Pigment_sox6_high, retina pigmented epithelium marker      1
mNC_nohox, periderm marker                                 1
notocord marker                                            1
Name: count, Length: 110, dtype: int64

Calculate Leiden Cluster Average Expression Signatures

ser_counts = adata.obs["leiden"].value_counts()
ser_counts.name = "cell counts"
meta_leiden = pd.DataFrame(ser_counts)

cat_name = "leiden"
sig_leiden = pd.DataFrame(
    columns=adata.var_names, index=adata.obs[cat_name].cat.categories
)
for clust in adata.obs[cat_name].cat.categories:
    sig_leiden.loc[clust] = adata[adata.obs[cat_name].isin([clust]), :].X.mean(0)
sig_leiden = sig_leiden.transpose()
leiden_clusters = ["Leiden-" + str(x) for x in sig_leiden.columns.tolist()]
sig_leiden.columns = leiden_clusters
meta_leiden.index = sig_leiden.columns.tolist()
meta_leiden["leiden"] = pd.Series(
    meta_leiden.index.tolist(), index=meta_leiden.index.tolist()
)

Assign Cell Type Based on Top Expressed Marker Genes

meta_gene = pd.DataFrame(index=sig_leiden.index.tolist())
meta_gene["info"] = pd.Series("", index=meta_gene.index.tolist())
meta_gene["Markers"] = pd.Series("N.A.", index=sig_leiden.index.tolist())
meta_gene.loc[common_marker_genes, "Markers"] = df_ref_panel.loc[
    common_marker_genes, "Function"
]

meta_leiden["Cell_Type"] = pd.Series("N.A.", index=meta_leiden.index.tolist())
num_top_genes = 30
for inst_cluster in sig_leiden.columns.tolist():
    top_genes = (
        sig_leiden[inst_cluster]
        .sort_values(ascending=False)
        .index.tolist()[:num_top_genes]
    )

    inst_ser = meta_gene.loc[top_genes, "Markers"]
    inst_ser = inst_ser[inst_ser != "N.A."]
    ser_counts = inst_ser.value_counts()

    max_count = ser_counts.max()

    max_cat = "_".join(sorted(ser_counts[ser_counts == max_count].index.tolist()))
    max_cat = max_cat.replace(" marker", "").replace(" ", "-")

    print(inst_cluster, max_cat)
    meta_leiden.loc[inst_cluster, "Cell_Type"] = max_cat

# rename clusters
meta_leiden["name"] = meta_leiden.apply(
    lambda x: x["Cell_Type"] + "_" + x["leiden"], axis=1
)
leiden_names = meta_leiden["name"].values.tolist()
meta_leiden.index = leiden_names

# transfer cell type labels to single cells
leiden_to_cell_type = deepcopy(meta_leiden)
leiden_to_cell_type.set_index("leiden", inplace=True)
leiden_to_cell_type.index.name = None

adata.obs["Cell_Type"] = adata.obs["leiden"].apply(
    lambda x: leiden_to_cell_type.loc["Leiden-" + str(x), "Cell_Type"]
)
adata.obs["Cluster"] = adata.obs["leiden"].apply(
    lambda x: leiden_to_cell_type.loc["Leiden-" + str(x), "name"]
)

Leiden-0 mNC_arch2_tailbud---spinal-cord
Leiden-1 mesoderm---adaxial-cells_tailbud---PSM
Leiden-2 NPB_nohox_cycling,dNC_nohox_cycling_differentiating-neurons,differentiating-neurons---rohon-beard,epidermal---olfactory-placode,differentiating-neurons---eomesa_epidermal---otic-placode_epiphysis_mNC_arch2_neural---diencephalon-,optic-primordium_neural---hindbrain_neural---hindbrain-ventral-nkx6.2_neural---midbrain-ventral-nkx6.2_neural---midbrain-ventral-nkx6.2,neural---hindbrain-ventral-nkx6.2_neural---midbrain,neural---ventral-hindbrain_tailbud---spinal-cord
Leiden-3 Mutant_nohox_early_NPB_nohox_cycling_NPB_nohox_cycling,dNC_nohox_cycling_Pigment_Pigment_gch2_high_dNC_nohox_epidermal---otic-placode_epiphysis_mNC_hox34_neural---hindbrain_neural---midbrain-ventral-nkx6.2_neural---midbrain,neural---ventral-hindbrain
Leiden-4 mNC_head_mesenchymal_mesoderm---adaxial-cells
Leiden-5 Mutant_nohox_early_dNC_hox34_neural---dorsal-hindbrain
Leiden-6 tailbud---PSM
Leiden-7 NPB_hox3_dNC_hox34_tailbud---spinal-cord
Leiden-8 lens-placode
Leiden-9 NC_trunk
Leiden-10 Mutant_nohox_12_22ss
Leiden-11 mNC_head_mesenchymal
Leiden-12 Mutant_nohox_pigment_dNC_hoxa2b_mNC_nohox
Leiden-13 Mutant_nohox_pigment_mNC_head_mesenchymal_mesoderm---lateral-plate---cxcl12a
Leiden-14 Mutant_hox3_mNC_head_mesenchymal_pharyngeal-arch
Leiden-15 mNC_nohox
Leiden-16 NPB_nohox_cycling,dNC_nohox_cycling_Pigment_sox6_high_epiphysis_mNC_arch2,Mutant_hox3_mNC_hox34_mNC_nohox_neural---anterior_neural---diencephalon-,neural---telencephalon_neural---diencephalon-,optic-primordium_neural---dorsal-hindbrain_neural---hindbrain_neural---midbrain-ventral-nkx6.2_neural---midbrain-ventral-nkx6.2,neural---hindbrain-ventral-nkx6.2_neural---midbrain,neural---ventral-hindbrain_neural---ventral-hindbrain
Leiden-17 mesoderm---adaxial-cells_tailbud---PSM
Leiden-18 NC_trunk_mNC_head_mesenchymal
Leiden-19 Mutant_nohox_12_22ss_NC_trunk_Pigment_endoderm_epidermal---foxi3a_epidermal---gbx2_epidermal---pfn1_ionocyte---ca2_mNC_arch1,-anterior-neural-ridge_mNC_arch2_mNC_head_mesenchymal_mNC_head_mesenchymal,-Mutant_hox3_mNC_nohox_mNC_nohox,-periderm_mNC_vagal,-Mutant_pigment_macrophage_neural-crest_neural-crest,neural-crest---crestin_retina-pigmented-epithelium
Leiden-20 NC_trunk_NPB_hox3
Leiden-21 mNC_nohox
Leiden-22 dNC_hoxa2b_neural---midbrain-ventral-nkx6.2
Leiden-23 mNC_head_mesenchymal
Leiden-24 dNC_hoxa2b
Leiden-25 mNC_nohox
Leiden-26 dNC_hoxa2b_endothelial
Leiden-27 Mutant_hox2,-endoderm_Mutant_hox2,Mutant_pigment_NPB_hox3,-mNC_arch1_Pigment_dNC_hox34_endoderm_heart-field,pectoral-fin-field_mNC_arch1,-epidermal---pfn1_mNC_hox34,-prechordal-plate---hatching-gland_mNC_vagal,Mutant_nohox_early_macrophage---ly75_macrophage_mesoderm---adaxial-cells_mesoderm---lateral-plate---cxcl12a,mesoderm---heart-field_otic-placode_retina-pigmented-epithelium_retina-pigmented-epithelium,-Pigment_sox6_high
Leiden-28 Mutant_nohox_12_22ss
Leiden-29 endothelial
Leiden-30 dNC_hoxa2b_epidermal-anterior
Leiden-31 NC_trunk_mNC_vagal
Leiden-32 dNC_hox34
Leiden-33 Mutant_hox2,Mutant_pigment_Mutant_nohox_pigment_Mutant_nohox_pigment,-neural-crest---grem2_NC_trunk_dNC_hox34_epiphysis_lens-placode_mNC_arch1_mNC_hox34,-prechordal-plate---hatching-gland_mNC_nohox_mesoderm---lateral-plate---cxcl12a,mesoderm---heart-field_pharyngeal-arch_prechordal-plate---hatching-gland_retina-pigmented-epithelium
Leiden-34 lens-placode
Leiden-35 heart-mature_lens-placode_mesoderm---adaxial-cells
Leiden-36 NC_trunk
Leiden-37 mNC_vagal_mesoderm---adaxial-cells

Save anndata

adata

AnnData object with n_obs × n_vars = 106333 × 300
    obs: 'fov', 'volume', 'min_x', 'min_y', 'max_x', 'max_y', 'anisotropy', 'transcript_count', 'perimeter_area_ratio', 'solidity', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'pct_counts_in_top_50_genes', 'pct_counts_in_top_100_genes', 'pct_counts_in_top_200_genes', 'pct_counts_in_top_280_genes', 'n_counts', 'leiden', 'regions', 'Cell_Type', 'Cluster'
    var: 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts', 'mean', 'std'
    uns: 'log1p', 'pca', 'neighbors', 'umap', 'leiden', 'leiden_colors', 'regions_colors', 'spatial_neighbors', 'leiden_centrality_scores', 'leiden_nhood_enrichment', 'leiden_ripley_L'
    obsm: 'blank_genes', 'spatial', 'X_pca', 'X_umap'
    varm: 'PCs'
    layers: 'counts'
    obsp: 'distances', 'connectivities', 'spatial_connectivities', 'spatial_distances'

clustered_filename = '/home/huzhiy/projects_ox/merscope/merscope_run5/data/anndata/20240715_run5_minexp10_squidpy_adata_clustered.hdf5'
adata.write_h5ad(clustered_filename)

adata.obs["regions"].value_counts()

regions
Region1    21119
Region2    18380
Region5    18128
Region0    18113
Region3    16069
Region4    14524
Name: count, dtype: int64

add manual annotation (not in use)

# anno = pd.read_csv("/home/huzhiy/projects_ox/merscope/analysis/merscope_run3/data/20240522_run3_manual_curation_cellType20240424.tsv", sep='\t')
# anno

ad_sp = adata
# Convert 'leiden' to string if it's not already, to ensure matching types with AnnData
anno['leiden'] = anno['leiden'].astype(str)
# Create a dictionary mapping 'leiden' to 'cell_type'
leiden_to_celltype = dict(zip(anno['leiden'], anno['cell_type']))
# Ensure the 'leiden' in AnnData is a string, if it's numeric or otherwise
ad_sp.obs['leiden'] = ad_sp.obs['leiden'].astype(str)

# Map cell_type using the dictionary
ad_sp.obs['cell_type'] = ad_sp.obs['leiden'].map(leiden_to_celltype)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[71], line 3
      1 ad_sp = adata
      2 # Convert 'leiden' to string if it's not already, to ensure matching types with AnnData
----> 3 anno['leiden'] = anno['leiden'].astype(str)
      4 # Create a dictionary mapping 'leiden' to 'cell_type'
      5 leiden_to_celltype = dict(zip(anno['leiden'], anno['cell_type']))

NameError: name 'anno' is not defined

#Step 1: Plot the Distribution
# Let's start by plotting the distribution of the y-coordinates (second column) from your spatial data to understand the range and central tendencies.
import matplotlib.pyplot as plt
import numpy as np

# Extracting the second column (y-coordinates) from the 'spatial' data
y_coordinates = ad_sp.obsm['spatial'][:, 1]

# Plotting the distribution of y-coordinates
plt.figure(figsize=(10, 6))
plt.hist(y_coordinates, bins=50, color='skyblue')
plt.title('Distribution of Y-coordinates in Spatial Data')
plt.xlabel('Y-coordinate values')
plt.ylabel('Frequency')
plt.grid(True)
plt.show()

sq.pl.spatial_scatter(
    ad_sp[ad_sp.obsm['spatial'][:, 1] <= 5000].copy(),
    shape=None,
    color=[
        "cell_type",
    ],figsize=(16,12), size = 1,
    wspace=0.4,
)

sq.pl.spatial_scatter(
    ad_sp[ad_sp.obsm['spatial'][:, 1] <= 5000].copy(),
    color="cell_type",
    groups=[ "neural_crest","neural _crest/neural/EVL","optic","otic_placode","neural_dorsal","pharyngeal arch"],
    shape=None,
    figsize=(7.6,12), size = 0.5
)

sq.pl.spatial_scatter(
    ad_sp[ad_sp.obsm['spatial'][:, 1] > 6100].copy(),
    shape=None,
    color=[
        "cell_type",
    ],figsize=(16,12), size = 1,
    wspace=0.4,
)

sq.pl.spatial_scatter(
    ad_sp[ad_sp.obsm['spatial'][:, 1] > 6100].copy(),
    color="cell_type",
    groups=[ "neural_crest","neural _crest/neural/EVL","optic","otic_placode","neural_dorsal","pharyngeal arch"],
    shape=None,
    figsize=(7.6,12), size = 0.5
)